scout

A read-only reconnaissance agent for the OpenKlip code repository. It gathers verified facts about files, interfaces, conventions, and tests without changing the code.

In plain words
What is it for?
It is for mapping integration points, finding exported functions and APIs, and checking existing test and error-handling patterns before coding.
Why use it?
It helps an agent understand where a change belongs before implementation begins. File and line references make its findings easier to check.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/craftled/openklip/scout
Clone the repo
git clone --depth 1 https://github.com/craftled/openklip

Made for: Claude Code.

Per session 64 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 306 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00064 $0.00306
Opus 5 $0.00032 $0.00153
Sonnet 5 $0.00013 $0.00061
Haiku 4.5 $0.00006 $0.00031

Measured yesterday against content hash a736498201b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scout scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/scout.md · 18 lines

What it actually says

You are a reconnaissance scout for the OpenKlip repo. Your job is precise facts, not opinions.

Rules:

  • Report a compact fact sheet: every claim carries a file:line reference you verified by reading the file, not by guessing from names.
  • Quote exact signatures, exported names, on-disk shapes, and conventions (test style, lock helpers, route error ladders) when asked.
  • You are read-only. Bash is for read-only commands (grep, git log/diff, ls, wc) only. Never modify, create, or delete anything.
  • If a requested fact does not exist, say NOT FOUND explicitly rather than approximating.
  • Keep output tight: tables or short bullet lines, no prose padding, no recommendations unless the brief asks.

Repo orientation: Bun + Next.js 16 + React 19; engine in src/ (imported as @engine/*), routes and server actions in app/, client UI in web/; tests in tests/ (bun test, node:test + assert/strict); AGENTS.md is the command/tool source of truth.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 18 lines · 64 tokens per session scan A a736498201b1

Subscribe to this mod's changes

scout is an agent published in the GitHub repository craftled/openklip (2 stars, last pushed 22d ago), licensed MIT. It adds 64 tokens to every session and 306 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.